💾 Archived View for theo.flounder.online › academic › gallery.gmi captured on 2023-07-10 at 13:13:37. Gemini links have been rewritten to link to archived content
⬅️ Previous capture (2023-06-14)
-=-=-=-=-=-=-
2023-06-02
A fun collection, demonstrating the capacity for AI/ML agents to learn:
An RL agent completes a 2D model moon landing in the lunar lander environment.
The k-means clustering algorithm converges to identify three groups within the data.
An RL agent trained using the Actor-Critic method successfully balances a pole attached to a movable cart.
A RL agent trained via Deep Q-Learning plays Breakout.
A script explores Stable Diffusion's diffusion noise space, showing different potential outputs for the prompt: "An oil paintings of cows in a field next to a windmill in Holland"
Linear Regression converges to a line of best fit.
An RL agent attempts to autonomously navigate along a modelled 2D highway with traffic.
An RL agent controls a robot arm, picking up cubes and holding them at an indicated point in space.
This simulated soft robot is controlled by an RL agent to traverse rightward.
https://github.com/CMU-Perceptual-Computing-Lab/openpose/raw/master/.github/media/pose_hands.gif
Pose estimation tracks the movements of co-author Tomas Simon as they test the system.
Various trained DQN agents act within varying atari environments.
Various trained Tensorflow models to try:
A collection of RL methods. Dynamic Programming, Temporal Difference learning, and Deep Q-learning, available to interact with across 3 environments:
---
Feel free to send comments & suggestions to me at:
